High-Quality Entity Segmentation

TL;DR

This paper introduces a new high-quality entity segmentation dataset and a novel query-based Transformer method, CropFormer, that effectively fuses multi-view image information to improve dense segmentation accuracy in diverse, high-resolution images.

Contribution

The paper presents a new dataset focused on high-quality dense segmentation in the wild and a novel Transformer architecture, CropFormer, for improved multi-view mask fusion in high-resolution images.

Findings

CropFormer achieves a 1.9 AP improvement on entity segmentation.

The dataset enables better generalization across diverse domains.

CropFormer enhances traditional segmentation tasks.

Abstract

Dense image segmentation tasks e.g., semantic, panoptic) are useful for image editing, but existing methods can hardly generalize well in an in-the-wild setting where there are unrestricted image domains, classes, and image resolution and quality variations. Motivated by these observations, we construct a new entity segmentation dataset, with a strong focus on high-quality dense segmentation in the wild. The dataset contains images spanning diverse image domains and entities, along with plentiful high-resolution images and high-quality mask annotations for training and testing. Given the high-quality and -resolution nature of the dataset, we propose CropFormer which is designed to tackle the intractability of instance-level segmentation on high-resolution images. It improves mask prediction by fusing high-res image crops that provide more fine-grained image details and the full image. CropFormer is the first query-based Transformer architecture that can effectively fuse mask predictions from multiple image views, by learning queries that effectively associate the same entities across the full image and its crop. With CropFormer, we achieve a significant AP gain of $1.9$ on the challenging entity segmentation task. Furthermore, CropFormer consistently improves the accuracy of traditional segmentation tasks and datasets. The dataset and code will be released at http://luqi.info/entityv2.github.io/.